INDEX

Explanations

user-friendly solutions to everyday problems

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CloseOperation

-0.69

argout

-0.69

AndEndTag

-0.68

 يتيمه

-0.67

 referrerpolicy

-0.65

 stället

-0.63

StoryboardSegue

-0.63

ddots

-0.62

TagMode

-0.60

StoreMessageInfo

-0.60

POSITIVE LOGITS

 myself

0.82

 sometimes

0.79

 tartalomajánló

0.75

my

0.72

 always

0.67

 occasionally

0.65

 Sometimes

0.65

 Whenever

0.65

Sometimes

0.64

Whenever

0.62

Activations Density 0.312%

user-friendly solutions to everyday problems

No Comments

No Known Activations